Update app.py

app.py

@@ -1,10 +1,36 @@
-from transformers import pipeline
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import streamlit as st
 
-pipe=pipeline("sentiment-analysis")
-text=st.text_area("Enter text")
+# Load GPT-2 model and tokenizer
+model_name = "gpt2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-if text:
-    out=pipe(text)
+# Streamlit app
+st.title("Blog Post Generator")
 
-    st.json(out)
+# User input
+prompt = st.text_area("Enter a blog post topic or starting sentence:")
+max_length = st.slider("Maximum length of generated text:", min_value=50, max_value=500, value=200, step=50)
+
+if prompt:
+    # Tokenize input
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+
+    # Generate text
+    with torch.no_grad():
+        output = model.generate(
+            input_ids,
+            max_length=max_length,
+            num_return_sequences=1,
+            no_repeat_ngram_size=2,
+            top_k=50,
+            top_p=0.95,
+            temperature=0.7
+        )
+
+    # Decode and display generated text
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    st.subheader("Generated Blog Post:")
+    st.write(generated_text)